PENG, Yifan (Evan Peng)

Postdoc Research Scholar at Stanford /

350 Jane Stanford Way, Stanford, CA 94305

[Stanford Profile] [Google Scholar] [LinkedIn] [Twitter]

I am a Postdoc Research Scholar in the Stanford Computational Imaging Laboratory, working with Gordon Wetzstein. I received my PhD in Computer Science from Imager Lab, UBC, working with Wolfgang Heidrich. During the PhD, I was a Visiting Student Researcher at Visual Computing Center, KAUST. I received both my MSc and BE in Optical Science and Engineering from State Key Lab of Modern Optical Instrumentation, Zhejiang University. My research interest lies in the interdisciplinary field of Optics, Graphics, and Vision, particularly with the focus of: Computational Optics, Photography, Sensing, and Display; Holographic Imaging/Display & VR/AR/MR; Low-level Computer Vision & Graphics & Artificial Intelligence.


Nov 2020

I am serving as the Session Chair of Near-eye Displays session for IEEE ISMAR 2020. Come and enjoy the excellent work at this amazing event.

Oct 2020

I am continuing to serve as the Technical Committee for SID Display Week 2021 Display Systems Track. Welcome to share your excellent work at this amazing event.

Sep 2020

An invited talk in OSA Frontiers in Optics 2020 on Holographic display and image synthesis for VRAR.

Aug 2020

My course on Deep optics: joint design of optics and image recovery algorithms for domain specific cameras is live at SIGGRAPH 2020. I’m joined by excellent instructors Gordon Wetzstein, Wolfgang Heidrich, and Ashok Veeraraghavan.

Aug 2020

My paper on Neural Holography is featured in Stanford Engineering News, in ExtremeTech Media Press, and in Nweon Media Press.

Jul 2020

I am serving as the Technical Committee for SPIE AR|VR|MR 2021. Welcome to share your excellent work at this amazing event.

Jun 2020

I am serving as the Science and Technology Program Committee for IEEE ISMAR 2020. Welcome to share your excellent work at this amazing event.

May 2020

I am serving as the Sub-conference Committee for SPIE Photonics Asia 2020 Optoelectronic Imaging and Multimedia Technology. Welcome to share your excellent work at this amazing event.

Featured Publications

Neural holography with camera-in-the-loop training

Yifan (Evan) Peng, Suyeon Choi, Nitish Padmanaban, Jonghyun Kim, Gordon Wetzstein


We develop an algorithmic CGH framework that uses camera-in-the-loop training to achieve unprecedented image fidelity and real-time framerates.

Learned diffractive achromat for full-spectrum imaging

Xiong Dun, Hayato Ikoma, Gordon Wetzstein, Zhanshan Wang, Xinbin Cheng, Yifan (Evan) Peng


We realize the joint learning of a diffractive achromat with a realistic aperture size and an image recovery neural network in an end-to-end manner across the full visible spectrum.

End-to-end learned, optically coded super-resolution SPAD camera

Qilin Sun, Jian Zhang, Xiong Dun, Bernard Ghanem, Yifan (Evan) Peng, Wolfgang Heidrich


We investigate a low-cost,and compact optical coding camera design that supports high-resolution image reconstructions from raw measurements with low pixel counts.

Deep optics for single-shot high-dynamic-range imaging

Christopher A. Metzler, Hayato Ikoma, Yifan (Evan) Peng, Gordon Wetzstein


We develop an end-to-end optimization of optics and image processing for snapshot HDR imaging.

Learned large field-of-view imaging with thin-plate optics

Yifan (Evan) Peng*, Qilin Sun*, Xiong Dun*, Gordon Wetzstein, Wolfgang Heidrich, Felix Heide


We propose a lens design and learned reconstruction architecture that provide an order of magnitude increase in field of view for computational imaging using a single thin-plate lens.

Overlap-add stereograms for holographic near-eye displays

Nitish Padmanaban, Yifan (Evan) Peng, Gordon Wetzstein


The overlap-add stereogram (OLAS) algorithm uses overlapping hogels to encode the view-dependent lighting effects of a light field into a hologram achieving better quality than other holographic stereograms.

Wirtinger holography for near-eye displays

Praneeth Chakravarthula, Yifan (Evan) Peng, Joel Kollin, Henry Fuchs, Felix Heide


We revisit complex Wirtinger derivatives and devleop a phase retrieval algorithm that leads to holographic reconstructions with an order of magnitude lower error, both in simulation and on an experimental prototype.

End-to-end optimization of optics and image processing

Vincent Sitzmann*, Steven Diamond*, Yifan (Evan) Peng*, Xiong Dun, Stephen Boyd, Wolfgang Heidrich, Felix Heide, Gordon Wetzstein


We jointly optimize high-level image processing and camera optics to design novel domain-specific cameras. This end-to-end design paradigm is beneficial in computational optics, imaging, and display.

Focal sweep imaging with multi-focal diffractive optics

Yifan (Evan) Peng, Xiong Dun, Qilin Sun, Felix Heide, Wolfgang Heidrich


We extend the concept of focal sweep from refractive optics to diffractive optics. Experimental results indicate that the depth-of-field can be significantly extended with fewer artifacts remaining.

Depth and transient imaging with compressive SPAD array cameras

Qilin Sun, Xiong Dun, Yifan Peng, Wolfgang Heidrich


We overcome the spatial resolution limit of SPAD arrays by employing a compressive sensing camera design. We suppress the noise while abstracting the phase and amplitude information, so as to realize a temporal resolution of a few tens of picoseconds.

Mix-and-match holography (aka. Multiplexing holograms)

Yifan (Evan) Peng, Xiong Dun, Qilin Sun, Wolfgang Heidrich,


We computationally design pairs of diffractive optical elements that encode multiple holograms or target images under different geometric alignments or pairings. This provides the extra bandwidth required to multiplex several images.

Revisiting cross-channel information transfer for chromatic aberration correction

Tiancheng Sun, Yifan (Evan) Peng, Wolfgang Heidrich


We revisit the pixel-wise similarity between different color channels of the image and accordingly propose a novel algorithm for correcting chromatic aberration based on this cross-channel correlation.

Encoded diffractive optics for full-spectrum computational imaging

Felix Heide, Qiang Fu, Yifan (Evan) Peng, Wolfgang Heidrichc

Nature Publishing Group Scientific Reports 16'

We introduce numerically optimized encoded phase masks in which different optical parameters such as focus or zoom can be accessed through changes in the mechanical alignment of a ultra-thin stack of two or more masks. This co-design of optics and computation enables tunable, full-spectrum imaging using thin optics.

The diffractive achromat: Full spectrum computational imaging with diffractive optics

Yifan (Evan) Peng, Qiang Fu, Felix Heide, Wolfgang Heidrich


The diffractive achromat is a computationally optimized diffractive lens for full visible spectrum imaging, which is used jointly with a computational image reconstruction algorithm. We demonstrate high fidelity color diffractive-only imaging over the full visible spectrum with ultrathin flat lenses.

Computational imaging with lightweight diffractive-refractive optics

Yifan (Evan) Peng, Qiang Fu, Hadi Amata, Shuochen Su, Felix Heide, and Wolfgang Heidrich

OSA Optics Express 15'

We jointly design lightweight diffractive-refractive optics and post-processing algorithms to enable imaging under white light illumination.

Other Publications

Highly efficient waveguide display with space-variant volume holographic gratings

Chao Yu, Yifan Peng, Qing Zhao, Haifeng Li, and Xu Liu

OSA Applied Optics 17'

We propose a waveguide display based on space-variant volume holographic gratings (SVVHGs), achieving high efficiency and large FOV at the same time.

Beam shaping for multicolour LEDs with diffractive optical elements

Chao Yu, Yifan Peng, Tianyi Guo, Qiang Fu, Haifeng Li, Xu Liu

Taylor & Francis Journal of Modern Optics 17'

We propsoe an improved particle swarm optimization for the design of ultra-thin diffractive optical elements enabling multicolour beam shaping functionality. Pre-optimized initial structures and adaptive weight strategy achieve better and identical shaping performance for multiple colours.

Towards VR and AR: 360 light field display with mid-air interaction

Chen Su, Yifan Peng, Qing Zhong, Haifeng Li, Rui Wang, Wolfgang Heidrich, Xu Liu

ACM SIGGRAPH Asia E-tech 16'

We present a 360-deg. light field display to visualize 3D objects above the table-top screen, and provide a graspable and measurable virtual or augmented reality environment. Multiple users mid-air interactions based on their virtual measurement perception are enabled.

Optimized image synthesis for multi-projector-type light field display

Qing Zhong, Yifan Peng, Haifeng Li, and Xu Liu

IEEE Journal of Display Tech 16'

We introduce a weighted average optimization to the image synthesis process of light field displays, aiming to tradeoff the reconstructed depth range and the image sharpness without changing the hardware configuration, particularly for multi-projector-type light field displays.

Interactive performance animation for VR/AR using low-cost motion capture

Yifan Peng, Chen Su, Wolfgang Heidrich

SID Display Week Symposium 16'

We evaluate a robust 3D interactive approach for creating performance animation using a low?cost motion capture device. Our approach effectively combines hand motion capture, interactive locomotion control, and user-editing animation editing.

Gray-scale enhancement for time-mulitiplexing light field rendering

Chen Su, Qing Zhong, Yifan Peng, Liang Xu, Rui Wang, Haifeng Li, and Xu Liu

OSA Optics Express 15'

The proposed 3D ordered-dithering algorithm presents better visual perception than the conventional halftone algorithms with respect to grayscale representation, and is flexible to be applied in different time-multiplexing light field display systems.

Multi-LCDs based intergral light field display

Yifan Peng, Haifeng Li, Qing Zhong, and Xu Liu

OSA Applied Optics 13'

We achieve a light field three-dimensional display with a large viewing angular range based on spliced multi-LCDs. By measuring the coordinate distributions, calibration is implemented considering both imaging aberration and geometrical inaccuracy of the whole system.

Projector array based large-scale light field display

Qing Zhong, Yifan Peng, Haifeng Li, Chen Su, Weidong Shen, and Xu Liu

OSA Applied Optics 13'

We proposed an optimized reconstruction algorithm that unifies the conventional multiview and light-field reconstruction algorithms, which can indicate the perfromance difference when switching from multiview to light-field reconstruction. A prototype consisting of 60 projectors with an arc diffuser screen is constructed.

Spinning type omnidirectional light field reconstruction

Xinxing Xia, Xu Liu, Haifeng Li, Zhenrong Zheng, Han Wang, Yifan Peng, and Weidong Shen

OSA Optics Express 13'

Using light field reconstruction technique, we display a floating 3D scene in the air, which is 360-degree surrounding viewable with correct occlusion effect. The prototype is achieved and the true 3D color animation image has been presented vividly.


ACM SIGGRAPH 2014 2015 2016 2017 2018 2019 2020
ACM SIGGRAPH Asia 2016 2017 2018 2019 2020
IEEE International Symposium on Mixed and Augmented Reality (ISMAR) 2020
IEEE Computer Vision and Pattern Recognition (CVPR) 2017 2018 2019
IEEE International Conference on Computer Vision (ICCV) 2017
IEEE International Conference on Computational Photography (ICCP) 2016 2017 2018 2020
SID Display Week 2011-2014 2016 2018 2019
OSA Imaging and Applied Optics Congress 2020
OSA Frontiers in Optics (FiO) 2020
Computational Imaging (Wetzlar Networking) at Leica Camera World 2019
GAMES: Graphics And Mixed Environment Seminar (Webinar) 2020